The 3D semantic labeling task involves predicting a semantic labeling of a 3D scan mesh.

Evaluation and metrics

Our evaluation ranks all methods according to the PASCAL VOC intersection-over-union metric (IoU). IoU = TP/(TP+FP+FN), where TP, FP, and FN are the numbers of true positive, false positive, and false negative pixels, respectively. Predicted labels are evaluated per-vertex over the respective 3D scan mesh; for 3D approaches that operate on other representations like grids or points, the predicted labels should be mapped onto the mesh vertices (e.g., one such example for grid to mesh vertices is provided in the evaluation helpers).



This table lists the benchmark results for the 3D semantic label scenario.


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
PTv3 ScanNet0.794 10.941 30.813 160.851 70.782 50.890 20.597 10.916 10.696 70.713 30.979 10.635 10.384 20.793 20.907 60.821 30.790 290.696 100.967 30.903 10.805 1
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024
PonderV20.785 20.978 10.800 240.833 210.788 30.853 140.545 150.910 40.713 10.705 40.979 10.596 50.390 10.769 100.832 390.821 30.792 280.730 10.975 10.897 30.785 3
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm.
Mix3Dpermissive0.781 30.964 20.855 10.843 150.781 60.858 100.575 50.831 300.685 120.714 20.979 10.594 60.310 250.801 10.892 140.841 20.819 30.723 40.940 120.887 50.725 21
Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann: Mix3D: Out-of-Context Data Augmentation for 3D Scenes. 3DV 2021 (Oral)
Swin3Dpermissive0.779 40.861 200.818 130.836 180.790 20.875 30.576 40.905 50.704 40.739 10.969 90.611 20.349 100.756 190.958 10.702 420.805 130.708 70.916 300.898 20.801 2
ResLFE_HDS0.772 50.939 40.824 60.854 60.771 80.840 280.564 90.900 70.686 110.677 100.961 150.537 280.348 110.769 100.903 80.785 90.815 50.676 190.939 130.880 100.772 7
PPT-SpUNet-Joint0.766 60.932 50.794 300.829 230.751 200.854 120.540 190.903 60.630 310.672 130.963 130.565 190.357 80.788 30.900 100.737 240.802 140.685 140.950 60.887 50.780 4
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024
OctFormerpermissive0.766 60.925 70.808 200.849 90.786 40.846 240.566 80.876 130.690 90.674 120.960 160.576 150.226 640.753 210.904 70.777 110.815 50.722 50.923 260.877 120.776 6
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023
OccuSeg+Semantic0.764 80.758 570.796 280.839 170.746 220.907 10.562 100.850 220.680 140.672 130.978 40.610 30.335 160.777 60.819 420.847 10.830 10.691 120.972 20.885 70.727 19
CU-Hybrid Net0.764 80.924 80.819 110.840 160.757 150.853 140.580 20.848 230.709 30.643 210.958 190.587 100.295 310.753 210.884 180.758 180.815 50.725 30.927 230.867 190.743 13
O-CNNpermissive0.762 100.924 80.823 70.844 140.770 90.852 160.577 30.847 250.711 20.640 250.958 190.592 70.217 700.762 150.888 150.758 180.813 90.726 20.932 210.868 180.744 12
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong: O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. SIGGRAPH 2017
OA-CNN-L_ScanNet200.756 110.783 430.826 50.858 40.776 70.837 310.548 140.896 100.649 230.675 110.962 140.586 110.335 160.771 90.802 460.770 140.787 310.691 120.936 160.880 100.761 9
PNE0.755 120.786 410.835 40.834 200.758 130.849 190.570 70.836 290.648 240.668 150.978 40.581 140.367 60.683 320.856 270.804 50.801 180.678 160.961 40.889 40.716 26
P. Hermosilla: Point Neighborhood Embeddings.
ConDaFormer0.755 120.927 60.822 80.836 180.801 10.849 190.516 290.864 190.651 220.680 90.958 190.584 130.282 390.759 170.855 290.728 260.802 140.678 160.880 560.873 170.756 10
Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Guisong Xia, Dacheng Tao: ConDaFormer : Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding. Neurips, 2023
PointTransformerV20.752 140.742 650.809 190.872 10.758 130.860 90.552 120.891 110.610 380.687 50.960 160.559 220.304 280.766 130.926 30.767 150.797 210.644 300.942 100.876 150.722 23
Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, Hengshuang Zhao: Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. NeurIPS 2022
DMF-Net0.752 140.906 120.793 320.802 380.689 370.825 430.556 110.867 150.681 130.602 410.960 160.555 240.365 70.779 50.859 240.747 210.795 250.717 60.917 290.856 270.764 8
C.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang: Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation. ICONIP 2023
BPNetcopyleft0.749 160.909 100.818 130.811 310.752 180.839 300.485 440.842 260.673 150.644 200.957 230.528 340.305 270.773 80.859 240.788 70.818 40.693 110.916 300.856 270.723 22
Wenbo Hu, Hengshuang Zhao, Li Jiang, Jiaya Jia, Tien-Tsin Wong: Bidirectional Projection Network for Cross Dimension Scene Understanding. CVPR 2021 (Oral)
PointConvFormer0.749 160.793 390.790 330.807 340.750 210.856 110.524 250.881 120.588 500.642 240.977 70.591 80.274 440.781 40.929 20.804 50.796 220.642 310.947 80.885 70.715 27
Wenxuan Wu, Qi Shan, Li Fuxin: PointConvFormer: Revenge of the Point-based Convolution.
MSP0.748 180.623 910.804 220.859 30.745 230.824 450.501 340.912 30.690 90.685 70.956 240.567 180.320 220.768 120.918 40.720 310.802 140.676 190.921 270.881 90.779 5
StratifiedFormerpermissive0.747 190.901 130.803 230.845 130.757 150.846 240.512 300.825 330.696 70.645 190.956 240.576 150.262 550.744 260.861 230.742 220.770 400.705 80.899 420.860 240.734 14
Xin Lai*, Jianhui Liu*, Li Jiang, Liwei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia: Stratified Transformer for 3D Point Cloud Segmentation. CVPR 2022
Virtual MVFusion0.746 200.771 510.819 110.848 110.702 340.865 80.397 820.899 80.699 50.664 160.948 520.588 90.330 180.746 250.851 330.764 160.796 220.704 90.935 170.866 200.728 17
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru: Virtual Multi-view Fusion for 3D Semantic Segmentation. ECCV 2020
VMNetpermissive0.746 200.870 180.838 20.858 40.729 280.850 180.501 340.874 140.587 510.658 170.956 240.564 200.299 290.765 140.900 100.716 340.812 100.631 360.939 130.858 250.709 28
Zeyu HU, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai: VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. ICCV 2021 (Oral)
Retro-FPN0.744 220.842 260.800 240.767 520.740 240.836 330.541 170.914 20.672 160.626 290.958 190.552 250.272 460.777 60.886 170.696 430.801 180.674 220.941 110.858 250.717 24
Peng Xiang*, Xin Wen*, Yu-Shen Liu, Hui Zhang, Yi Fang, Zhizhong Han: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation. ICCV 2023
EQ-Net0.743 230.620 920.799 270.849 90.730 270.822 470.493 410.897 90.664 170.681 80.955 270.562 210.378 30.760 160.903 80.738 230.801 180.673 230.907 340.877 120.745 11
Zetong Yang*, Li Jiang*, Yanan Sun, Bernt Schiele, Jiaya JIa: A Unified Query-based Paradigm for Point Cloud Understanding. CVPR 2022
SAT0.742 240.860 210.765 460.819 260.769 100.848 210.533 210.829 310.663 180.631 280.955 270.586 110.274 440.753 210.896 120.729 250.760 470.666 250.921 270.855 290.733 15
LRPNet0.742 240.816 340.806 210.807 340.752 180.828 410.575 50.839 280.699 50.637 260.954 330.520 370.320 220.755 200.834 370.760 170.772 370.676 190.915 320.862 220.717 24
LargeKernel3D0.739 260.909 100.820 100.806 360.740 240.852 160.545 150.826 320.594 490.643 210.955 270.541 270.263 540.723 300.858 260.775 130.767 410.678 160.933 190.848 340.694 33
Yukang Chen*, Jianhui Liu*, Xiangyu Zhang, Xiaojuan Qi, Jiaya Jia: LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs. CVPR 2023
RPN0.736 270.776 470.790 330.851 70.754 170.854 120.491 430.866 170.596 480.686 60.955 270.536 290.342 130.624 470.869 200.787 80.802 140.628 370.927 230.875 160.704 30
MinkowskiNetpermissive0.736 270.859 220.818 130.832 220.709 320.840 280.521 270.853 210.660 200.643 210.951 420.544 260.286 370.731 280.893 130.675 520.772 370.683 150.874 630.852 320.727 19
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019
IPCA0.731 290.890 140.837 30.864 20.726 290.873 40.530 240.824 340.489 840.647 180.978 40.609 40.336 150.624 470.733 550.758 180.776 350.570 620.949 70.877 120.728 17
PointTransformer++0.725 300.727 730.811 180.819 260.765 110.841 270.502 330.814 390.621 340.623 310.955 270.556 230.284 380.620 490.866 210.781 100.757 510.648 280.932 210.862 220.709 28
SparseConvNet0.725 300.647 880.821 90.846 120.721 300.869 50.533 210.754 550.603 440.614 330.955 270.572 170.325 200.710 310.870 190.724 290.823 20.628 370.934 180.865 210.683 36
MatchingNet0.724 320.812 360.812 170.810 320.735 260.834 350.495 400.860 200.572 580.602 410.954 330.512 390.280 410.757 180.845 350.725 280.780 330.606 470.937 150.851 330.700 32
INS-Conv-semantic0.717 330.751 600.759 490.812 300.704 330.868 60.537 200.842 260.609 400.608 370.953 360.534 310.293 320.616 500.864 220.719 330.793 260.640 320.933 190.845 380.663 42
PointMetaBase0.714 340.835 270.785 350.821 240.684 390.846 240.531 230.865 180.614 350.596 450.953 360.500 420.246 600.674 330.888 150.692 440.764 430.624 390.849 780.844 390.675 38
contrastBoundarypermissive0.705 350.769 540.775 400.809 330.687 380.820 500.439 700.812 400.661 190.591 470.945 600.515 380.171 880.633 440.856 270.720 310.796 220.668 240.889 490.847 350.689 34
Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao: Contrastive Boundary Learning for Point Cloud Segmentation. CVPR2022
ClickSeg_Semantic0.703 360.774 490.800 240.793 430.760 120.847 230.471 480.802 430.463 910.634 270.968 110.491 450.271 480.726 290.910 50.706 380.815 50.551 740.878 570.833 400.570 74
RFCR0.702 370.889 150.745 600.813 290.672 420.818 540.493 410.815 380.623 320.610 350.947 540.470 540.249 590.594 530.848 340.705 390.779 340.646 290.892 470.823 460.611 57
Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma: Omni-Supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning. CVPR2021
One Thing One Click0.701 380.825 310.796 280.723 590.716 310.832 370.433 720.816 360.634 290.609 360.969 90.418 800.344 120.559 650.833 380.715 350.808 120.560 680.902 390.847 350.680 37
JSENetpermissive0.699 390.881 170.762 470.821 240.667 430.800 660.522 260.792 460.613 360.607 380.935 800.492 440.205 750.576 580.853 310.691 460.758 490.652 270.872 660.828 430.649 46
Zeyu HU, Mingmin Zhen, Xuyang BAI, Hongbo Fu, Chiew-lan Tai: JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. ECCV 2020
One-Thing-One-Click0.693 400.743 640.794 300.655 820.684 390.822 470.497 390.719 650.622 330.617 320.977 70.447 670.339 140.750 240.664 710.703 410.790 290.596 520.946 90.855 290.647 47
Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu: One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation. CVPR 2021
PicassoNet-IIpermissive0.692 410.732 690.772 410.786 440.677 410.866 70.517 280.848 230.509 770.626 290.952 400.536 290.225 660.545 710.704 620.689 490.810 110.564 670.903 380.854 310.729 16
Huan Lei, Naveed Akhtar, Mubarak Shah, and Ajmal Mian: Geometric feature learning for 3D meshes.
Feature_GeometricNetpermissive0.690 420.884 160.754 530.795 410.647 500.818 540.422 740.802 430.612 370.604 390.945 600.462 570.189 830.563 640.853 310.726 270.765 420.632 350.904 360.821 490.606 61
Kangcheng Liu, Ben M. Chen: https://arxiv.org/abs/2012.09439. arXiv Preprint
FusionNet0.688 430.704 780.741 640.754 560.656 450.829 390.501 340.741 600.609 400.548 550.950 460.522 360.371 40.633 440.756 500.715 350.771 390.623 400.861 740.814 520.658 43
Feihu Zhang, Jin Fang, Benjamin Wah, Philip Torr: Deep FusionNet for Point Cloud Semantic Segmentation. ECCV 2020
Feature-Geometry Netpermissive0.685 440.866 190.748 570.819 260.645 520.794 690.450 600.802 430.587 510.604 390.945 600.464 560.201 780.554 670.840 360.723 300.732 610.602 500.907 340.822 480.603 64
KP-FCNN0.684 450.847 250.758 510.784 460.647 500.814 570.473 470.772 490.605 420.594 460.935 800.450 650.181 860.587 540.805 450.690 470.785 320.614 430.882 530.819 500.632 53
H. Thomas, C. Qi, J. Deschaud, B. Marcotegui, F. Goulette, L. Guibas.: KPConv: Flexible and Deformable Convolution for Point Clouds. ICCV 2019
DGNet0.684 450.712 770.784 360.782 480.658 440.835 340.499 380.823 350.641 260.597 440.950 460.487 470.281 400.575 590.619 750.647 650.764 430.620 420.871 690.846 370.688 35
VACNN++0.684 450.728 720.757 520.776 490.690 350.804 640.464 530.816 360.577 570.587 480.945 600.508 410.276 430.671 340.710 600.663 570.750 550.589 570.881 540.832 420.653 45
Superpoint Network0.683 480.851 240.728 680.800 400.653 470.806 620.468 500.804 410.572 580.602 410.946 570.453 640.239 630.519 760.822 400.689 490.762 460.595 540.895 450.827 440.630 54
PointContrast_LA_SEM0.683 480.757 580.784 360.786 440.639 540.824 450.408 770.775 480.604 430.541 570.934 840.532 320.269 500.552 680.777 480.645 680.793 260.640 320.913 330.824 450.671 39
VI-PointConv0.676 500.770 530.754 530.783 470.621 580.814 570.552 120.758 530.571 600.557 530.954 330.529 330.268 520.530 740.682 660.675 520.719 640.603 490.888 500.833 400.665 41
Xingyi Li, Wenxuan Wu, Xiaoli Z. Fern, Li Fuxin: The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions.
ROSMRF3D0.673 510.789 400.748 570.763 540.635 560.814 570.407 790.747 570.581 550.573 500.950 460.484 480.271 480.607 510.754 510.649 620.774 360.596 520.883 520.823 460.606 61
SALANet0.670 520.816 340.770 440.768 510.652 480.807 610.451 570.747 570.659 210.545 560.924 900.473 530.149 980.571 610.811 440.635 710.746 560.623 400.892 470.794 650.570 74
O3DSeg0.668 530.822 320.771 430.496 1020.651 490.833 360.541 170.761 520.555 660.611 340.966 120.489 460.370 50.388 960.580 780.776 120.751 530.570 620.956 50.817 510.646 48
PointASNLpermissive0.666 540.703 790.781 380.751 580.655 460.830 380.471 480.769 500.474 870.537 590.951 420.475 520.279 420.635 420.698 650.675 520.751 530.553 730.816 850.806 560.703 31
Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui: PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. CVPR 2020
PointConvpermissive0.666 540.781 440.759 490.699 670.644 530.822 470.475 460.779 470.564 630.504 730.953 360.428 740.203 770.586 560.754 510.661 580.753 520.588 580.902 390.813 540.642 49
Wenxuan Wu, Zhongang Qi, Li Fuxin: PointConv: Deep Convolutional Networks on 3D Point Clouds. CVPR 2019
PPCNN++permissive0.663 560.746 620.708 710.722 600.638 550.820 500.451 570.566 930.599 460.541 570.950 460.510 400.313 240.648 390.819 420.616 760.682 790.590 560.869 700.810 550.656 44
Pyunghwan Ahn, Juyoung Yang, Eojindl Yi, Chanho Lee, Junmo Kim: Projection-based Point Convolution for Efficient Point Cloud Segmentation. IEEE Access
DCM-Net0.658 570.778 450.702 740.806 360.619 590.813 600.468 500.693 730.494 800.524 650.941 720.449 660.298 300.510 780.821 410.675 520.727 630.568 650.826 830.803 590.637 51
Jonas Schult*, Francis Engelmann*, Theodora Kontogianni, Bastian Leibe: DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes. CVPR 2020 [Oral]
MVF-GNN0.658 570.558 990.751 550.655 820.690 350.722 910.453 560.867 150.579 560.576 490.893 1020.523 350.293 320.733 270.571 800.692 440.659 860.606 470.875 600.804 580.668 40
HPGCNN0.656 590.698 810.743 620.650 840.564 760.820 500.505 320.758 530.631 300.479 770.945 600.480 500.226 640.572 600.774 490.690 470.735 590.614 430.853 770.776 800.597 67
Jisheng Dang, Qingyong Hu, Yulan Guo, Jun Yang: HPGCNN.
SAFNet-segpermissive0.654 600.752 590.734 660.664 800.583 710.815 560.399 810.754 550.639 270.535 610.942 700.470 540.309 260.665 350.539 820.650 610.708 690.635 340.857 760.793 670.642 49
Linqing Zhao, Jiwen Lu, Jie Zhou: Similarity-Aware Fusion Network for 3D Semantic Segmentation. IROS 2021
RandLA-Netpermissive0.645 610.778 450.731 670.699 670.577 720.829 390.446 620.736 610.477 860.523 670.945 600.454 610.269 500.484 860.749 540.618 740.738 570.599 510.827 820.792 700.621 56
PointConv-SFPN0.641 620.776 470.703 730.721 610.557 790.826 420.451 570.672 780.563 640.483 760.943 690.425 770.162 930.644 400.726 560.659 590.709 680.572 610.875 600.786 750.559 80
MVPNetpermissive0.641 620.831 280.715 690.671 770.590 670.781 750.394 830.679 750.642 250.553 540.937 770.462 570.256 560.649 380.406 960.626 720.691 760.666 250.877 580.792 700.608 60
Maximilian Jaritz, Jiayuan Gu, Hao Su: Multi-view PointNet for 3D Scene Understanding. GMDL Workshop, ICCV 2019
PointMRNet0.640 640.717 760.701 750.692 700.576 730.801 650.467 520.716 660.563 640.459 830.953 360.429 730.169 900.581 570.854 300.605 770.710 660.550 750.894 460.793 670.575 72
FPConvpermissive0.639 650.785 420.760 480.713 650.603 620.798 670.392 840.534 980.603 440.524 650.948 520.457 590.250 580.538 720.723 580.598 810.696 740.614 430.872 660.799 600.567 77
Yiqun Lin, Zizheng Yan, Haibin Huang, Dong Du, Ligang Liu, Shuguang Cui, Xiaoguang Han: FPConv: Learning Local Flattening for Point Convolution. CVPR 2020
PD-Net0.638 660.797 380.769 450.641 900.590 670.820 500.461 540.537 970.637 280.536 600.947 540.388 870.206 740.656 360.668 690.647 650.732 610.585 590.868 710.793 670.473 100
PointSPNet0.637 670.734 680.692 820.714 640.576 730.797 680.446 620.743 590.598 470.437 880.942 700.403 830.150 970.626 460.800 470.649 620.697 730.557 710.846 790.777 790.563 78
SConv0.636 680.830 290.697 780.752 570.572 750.780 770.445 640.716 660.529 700.530 620.951 420.446 680.170 890.507 810.666 700.636 700.682 790.541 810.886 510.799 600.594 68
Supervoxel-CNN0.635 690.656 860.711 700.719 620.613 600.757 860.444 670.765 510.534 690.566 510.928 880.478 510.272 460.636 410.531 840.664 560.645 900.508 880.864 730.792 700.611 57
joint point-basedpermissive0.634 700.614 930.778 390.667 790.633 570.825 430.420 750.804 410.467 890.561 520.951 420.494 430.291 340.566 620.458 910.579 870.764 430.559 700.838 800.814 520.598 66
Hung-Yueh Chiang, Yen-Liang Lin, Yueh-Cheng Liu, Winston H. Hsu: A Unified Point-Based Framework for 3D Segmentation. 3DV 2019
PointMTL0.632 710.731 700.688 850.675 740.591 660.784 740.444 670.565 940.610 380.492 740.949 500.456 600.254 570.587 540.706 610.599 800.665 850.612 460.868 710.791 730.579 71
3DSM_DMMF0.631 720.626 900.745 600.801 390.607 610.751 870.506 310.729 640.565 620.491 750.866 1050.434 690.197 810.595 520.630 740.709 370.705 710.560 680.875 600.740 900.491 95
PointNet2-SFPN0.631 720.771 510.692 820.672 750.524 840.837 310.440 690.706 710.538 680.446 850.944 660.421 790.219 690.552 680.751 530.591 830.737 580.543 800.901 410.768 820.557 81
APCF-Net0.631 720.742 650.687 870.672 750.557 790.792 720.408 770.665 790.545 670.508 700.952 400.428 740.186 840.634 430.702 630.620 730.706 700.555 720.873 640.798 620.581 70
Haojia, Lin: Adaptive Pyramid Context Fusion for Point Cloud Perception. GRSL
FusionAwareConv0.630 750.604 950.741 640.766 530.590 670.747 880.501 340.734 620.503 790.527 630.919 940.454 610.323 210.550 700.420 950.678 510.688 770.544 780.896 440.795 640.627 55
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng, Kai Xu: Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. CVPR 2020
DenSeR0.628 760.800 370.625 980.719 620.545 810.806 620.445 640.597 870.448 940.519 680.938 760.481 490.328 190.489 850.499 890.657 600.759 480.592 550.881 540.797 630.634 52
SegGroup_sempermissive0.627 770.818 330.747 590.701 660.602 630.764 830.385 880.629 840.490 820.508 700.931 870.409 820.201 780.564 630.725 570.618 740.692 750.539 820.873 640.794 650.548 84
An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou: SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. TIP 2022
SIConv0.625 780.830 290.694 800.757 550.563 770.772 810.448 610.647 820.520 730.509 690.949 500.431 720.191 820.496 830.614 760.647 650.672 830.535 840.876 590.783 760.571 73
dtc_net0.625 780.703 790.751 550.794 420.535 820.848 210.480 450.676 770.528 710.469 800.944 660.454 610.004 1110.464 880.636 730.704 400.758 490.548 770.924 250.787 740.492 94
HPEIN0.618 800.729 710.668 880.647 860.597 650.766 820.414 760.680 740.520 730.525 640.946 570.432 700.215 710.493 840.599 770.638 690.617 950.570 620.897 430.806 560.605 63
Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia: Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. ICCV 2019
SPH3D-GCNpermissive0.610 810.858 230.772 410.489 1030.532 830.792 720.404 800.643 830.570 610.507 720.935 800.414 810.046 1080.510 780.702 630.602 790.705 710.549 760.859 750.773 810.534 87
Huan Lei, Naveed Akhtar, and Ajmal Mian: Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. TPAMI 2020
AttAN0.609 820.760 560.667 890.649 850.521 850.793 700.457 550.648 810.528 710.434 900.947 540.401 840.153 960.454 890.721 590.648 640.717 650.536 830.904 360.765 830.485 96
Gege Zhang, Qinghua Ma, Licheng Jiao, Fang Liu and Qigong Sun: AttAN: Attention Adversarial Networks for 3D Point Cloud Semantic Segmentation. IJCAI2020
wsss-transformer0.600 830.634 890.743 620.697 690.601 640.781 750.437 710.585 900.493 810.446 850.933 850.394 850.011 1100.654 370.661 720.603 780.733 600.526 850.832 810.761 850.480 97
LAP-D0.594 840.720 740.692 820.637 910.456 950.773 800.391 860.730 630.587 510.445 870.940 740.381 880.288 350.434 920.453 930.591 830.649 880.581 600.777 890.749 890.610 59
DPC0.592 850.720 740.700 760.602 950.480 910.762 850.380 890.713 690.585 540.437 880.940 740.369 900.288 350.434 920.509 880.590 850.639 930.567 660.772 910.755 870.592 69
Francis Engelmann, Theodora Kontogianni, Bastian Leibe: Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. ICRA 2020
CCRFNet0.589 860.766 550.659 930.683 720.470 940.740 900.387 870.620 860.490 820.476 780.922 920.355 930.245 610.511 770.511 870.571 880.643 910.493 920.872 660.762 840.600 65
ROSMRF0.580 870.772 500.707 720.681 730.563 770.764 830.362 910.515 990.465 900.465 820.936 790.427 760.207 730.438 900.577 790.536 910.675 820.486 930.723 970.779 770.524 90
SD-DETR0.576 880.746 620.609 1020.445 1070.517 860.643 1020.366 900.714 680.456 920.468 810.870 1040.432 700.264 530.558 660.674 670.586 860.688 770.482 940.739 950.733 920.537 86
SQN_0.1%0.569 890.676 830.696 790.657 810.497 870.779 780.424 730.548 950.515 750.376 950.902 1010.422 780.357 80.379 970.456 920.596 820.659 860.544 780.685 1000.665 1030.556 82
TextureNetpermissive0.566 900.672 850.664 900.671 770.494 890.719 920.445 640.678 760.411 1000.396 930.935 800.356 920.225 660.412 940.535 830.565 890.636 940.464 960.794 880.680 1000.568 76
Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkerhouser, Matthias Niessner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. CVPR
DVVNet0.562 910.648 870.700 760.770 500.586 700.687 960.333 950.650 800.514 760.475 790.906 980.359 910.223 680.340 990.442 940.422 1020.668 840.501 890.708 980.779 770.534 87
Pointnet++ & Featurepermissive0.557 920.735 670.661 920.686 710.491 900.744 890.392 840.539 960.451 930.375 960.946 570.376 890.205 750.403 950.356 990.553 900.643 910.497 900.824 840.756 860.515 91
GMLPs0.538 930.495 1040.693 810.647 860.471 930.793 700.300 980.477 1000.505 780.358 980.903 1000.327 960.081 1050.472 870.529 850.448 1000.710 660.509 860.746 930.737 910.554 83
PanopticFusion-label0.529 940.491 1050.688 850.604 940.386 1000.632 1030.225 1080.705 720.434 970.293 1040.815 1060.348 940.241 620.499 820.669 680.507 930.649 880.442 1020.796 870.602 1070.561 79
Gaku Narita, Takashi Seno, Tomoya Ishikawa, Yohsuke Kaji: PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things. IROS 2019 (to appear)
subcloud_weak0.516 950.676 830.591 1050.609 920.442 960.774 790.335 940.597 870.422 990.357 990.932 860.341 950.094 1040.298 1010.528 860.473 980.676 810.495 910.602 1060.721 950.349 107
Online SegFusion0.515 960.607 940.644 960.579 970.434 970.630 1040.353 920.628 850.440 950.410 910.762 1100.307 980.167 910.520 750.403 970.516 920.565 980.447 1000.678 1010.701 970.514 92
Davide Menini, Suryansh Kumar, Martin R. Oswald, Erik Sandstroem, Cristian Sminchisescu, Luc van Gool: A Real-Time Learning Framework for Joint 3D Reconstruction and Semantic Segmentation. Robotics and Automation Letters Submission
3DMV, FTSDF0.501 970.558 990.608 1030.424 1090.478 920.690 950.246 1040.586 890.468 880.450 840.911 960.394 850.160 940.438 900.212 1060.432 1010.541 1040.475 950.742 940.727 930.477 98
PCNN0.498 980.559 980.644 960.560 990.420 990.711 940.229 1060.414 1010.436 960.352 1000.941 720.324 970.155 950.238 1060.387 980.493 940.529 1050.509 860.813 860.751 880.504 93
Weakly-Openseg v30.489 990.749 610.664 900.646 880.496 880.559 1080.122 1110.577 910.257 1110.364 970.805 1070.198 1090.096 1030.510 780.496 900.361 1060.563 990.359 1090.777 890.644 1040.532 89
3DMV0.484 1000.484 1060.538 1070.643 890.424 980.606 1070.310 960.574 920.433 980.378 940.796 1080.301 990.214 720.537 730.208 1070.472 990.507 1080.413 1050.693 990.602 1070.539 85
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
PointCNN with RGBpermissive0.458 1010.577 970.611 1010.356 1110.321 1080.715 930.299 1000.376 1050.328 1070.319 1020.944 660.285 1010.164 920.216 1090.229 1040.484 960.545 1030.456 980.755 920.709 960.475 99
Yangyan Li, Rui Bu, Mingchao Sun, Baoquan Chen: PointCNN. NeurIPS 2018
FCPNpermissive0.447 1020.679 820.604 1040.578 980.380 1010.682 970.291 1010.106 1110.483 850.258 1090.920 930.258 1050.025 1090.231 1080.325 1000.480 970.560 1010.463 970.725 960.666 1020.231 111
Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari: Fully-Convolutional Point Networks for Large-Scale Point Clouds. ECCV 2018
DGCNN_reproducecopyleft0.446 1030.474 1070.623 990.463 1050.366 1030.651 1000.310 960.389 1040.349 1050.330 1010.937 770.271 1030.126 1000.285 1020.224 1050.350 1080.577 970.445 1010.625 1040.723 940.394 103
Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon: Dynamic Graph CNN for Learning on Point Clouds. TOG 2019
PNET20.442 1040.548 1010.548 1060.597 960.363 1040.628 1050.300 980.292 1060.374 1020.307 1030.881 1030.268 1040.186 840.238 1060.204 1080.407 1030.506 1090.449 990.667 1020.620 1060.462 101
SurfaceConvPF0.442 1040.505 1030.622 1000.380 1100.342 1060.654 990.227 1070.397 1030.367 1030.276 1060.924 900.240 1060.198 800.359 980.262 1020.366 1040.581 960.435 1030.640 1030.668 1010.398 102
Hao Pan, Shilin Liu, Yang Liu, Xin Tong: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames.
Tangent Convolutionspermissive0.438 1060.437 1090.646 950.474 1040.369 1020.645 1010.353 920.258 1080.282 1090.279 1050.918 950.298 1000.147 990.283 1030.294 1010.487 950.562 1000.427 1040.619 1050.633 1050.352 106
Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou: Tangent convolutions for dense prediction in 3d. CVPR 2018
3DWSSS0.425 1070.525 1020.647 940.522 1000.324 1070.488 1110.077 1120.712 700.353 1040.401 920.636 1120.281 1020.176 870.340 990.565 810.175 1120.551 1020.398 1060.370 1120.602 1070.361 105
SPLAT Netcopyleft0.393 1080.472 1080.511 1080.606 930.311 1090.656 980.245 1050.405 1020.328 1070.197 1100.927 890.227 1080.000 1130.001 1130.249 1030.271 1110.510 1060.383 1080.593 1070.699 980.267 109
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz: SPLATNet: Sparse Lattice Networks for Point Cloud Processing. CVPR 2018
ScanNet+FTSDF0.383 1090.297 1110.491 1090.432 1080.358 1050.612 1060.274 1020.116 1100.411 1000.265 1070.904 990.229 1070.079 1060.250 1040.185 1090.320 1090.510 1060.385 1070.548 1080.597 1100.394 103
PointNet++permissive0.339 1100.584 960.478 1100.458 1060.256 1110.360 1120.250 1030.247 1090.278 1100.261 1080.677 1110.183 1100.117 1010.212 1100.145 1110.364 1050.346 1120.232 1120.548 1080.523 1110.252 110
Charles R. Qi, Li Yi, Hao Su, Leonidas J. Guibas: pointnet++: deep hierarchical feature learning on point sets in a metric space.
SSC-UNetpermissive0.308 1110.353 1100.290 1120.278 1120.166 1120.553 1090.169 1100.286 1070.147 1120.148 1120.908 970.182 1110.064 1070.023 1120.018 1130.354 1070.363 1100.345 1100.546 1100.685 990.278 108
ScanNetpermissive0.306 1120.203 1120.366 1110.501 1010.311 1090.524 1100.211 1090.002 1130.342 1060.189 1110.786 1090.145 1120.102 1020.245 1050.152 1100.318 1100.348 1110.300 1110.460 1110.437 1120.182 112
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17
ERROR0.054 1130.000 1130.041 1130.172 1130.030 1130.062 1130.001 1130.035 1120.004 1130.051 1130.143 1130.019 1130.003 1120.041 1110.050 1120.003 1130.054 1130.018 1130.005 1130.264 1130.082 113